pc-screen-control copilot-instructions.md

Project instructions for PC Screen Control, a tool that lets an AI assistant interact with a computer screen while checking that actions go to the intended window. They describe its releases, packages, safety checks, and tests.

In plain words
What is it for?
Use them when developing or reviewing PC Screen Control, its installation packages, window checks, screen actions, or automated tests.
Why use it?
They help prevent commands or typed text from being sent to the wrong application, especially when a screen changes during a task.

Instructions file for GitHub Copilot

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/desteny-dev/pc-screen-control/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/desteny-dev/pc-screen-control

Made for: GitHub Copilot.

Per session 4,904 This file is loaded in full into every session.
When invoked 4,904 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.04904 $0.04904
Opus 5 $0.02452 $0.02452
Sonnet 5 $0.00981 $0.00981
Haiku 4.5 $0.00490 $0.00490

Measured 2d ago against content hash d37bae26af0c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pc-screen-control copilot-instructions.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.github/copilot-instructions.md · 385 lines

How it starts

The opening of the file, as written. The whole thing — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PC Screen Control — where this is going

Written by the maintainer. Read this before proposing changes.


Start here

Current state: v1.7.0 is released. 34 tools, 19 test files in CI on Python 3.9 / 3.11 / 3.13, all green. Two packages ship: pc-screen-control.mcpb, a one-click first install for Claude Desktop, and pc-screen-control-setup.zip with INSTALL.bat, which registers every MCP client it finds — Claude Desktop, the Store build, Claude Code and Codex — and is the only route that still works once Claude has blocked extension installs. Same server inside both.

Three releases in a row came from the same place: what the guard protects and what a person actually loses were not the same list.

1.3.0 — the guard knew whether the screen had moved, but not whether the foreground was still the window the assistant had declared. After a block ended mid-task those were the same answer, and a command meant for a terminal was typed into somebody's chat. The declared window is tracked separately now, taken from the call itself so no tool can forget it (tests/test_wrong_window.py).

1.3.1 — the check and the send cannot be one instruction. Seen once live: the check passed honestly and the keys landed elsewhere a fraction of a second later. Cannot be prevented; the silence after it can. send_keys reports off_target naming both windows.

1.3.2 — the person's own window could be closed, parked out of reach or minimised, because no tool knew which window they were sitting in; a window_title matching theirs instead of ours was the whole distance. It is now refused, an ambiguous title is refused rather than guessed for anything destructive, Alt+F4/Ctrl+W without a ref is refused, and a foreground that did not come back is reported on the next call whatever tool that is (tests/test_user_window.py).

1.3.3 — and then a live test of 1.3.2 showed the sharpest version of the same mistake: the release measured whether it had given the screen back, wrote the result into _RUECKGABE, and nothing ever read it. A comment said tools copy it into their reply; none did. set_guard block:'end' now returns handed_back, including in_front_now — what is actually in front, measured after the restore, as opposed to whether the call returned true.

Read the full file on GitHub · 385 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 385 lines · 4,904 tokens per session scan A d37bae26af0c

Subscribe to this mod's changes

pc-screen-control copilot-instructions.md is an instructions file published in the GitHub repository desteny-dev/pc-screen-control (2 stars, last pushed 26d ago), licensed MIT. It adds 4,904 tokens to every session, about $0.0245 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.